Create get_rewards() and define the action_space

[RusherRG]

get_rewards()
The current step() function in CodeSideEnv doesn't return/assign any reward for a particular action. A logic to calculate the rewards for the actions needs to be built and then get_rewards() that uses this logic has to be linked with step() to return reward

action_space
Define the action space of the environment as it makes it easier to define the scale of the input parameters while training RL agents. Also, create a env.action_space.sample() to return random actions.